Robotics Policy Research Engineer (Sim-to-Real & RL)

Zeromatter Technologies Inc; Mountain View (CA); On-site; USD 120,000 - 190,000; Full time

Job summary

Zeromatter Technologies Inc. is seeking a Robotics Research Engineer to design, train, and evaluate robotics policies—from imitation to reinforcement learning—to advance Zeromatter's simulation platform and its real-world validation across customer use cases.

You will collaborate with the Dynamics team to improve physics-based simulation fidelity, run experiments in simulation and the lab, and build scalable tooling in Python, Rust, and C++.

Qualifications

• Engineering degree or equivalent hands-on experience in robotics or related field.
• Experience training and evaluating robot learning policies in industry, lab, or academia.
• Hands-on experience with physical robots, data collection, experiments, and debugging hardware/software.
• Proficiency in Python, Rust, and/or C++, with ML frameworks such as PyTorch, TensorFlow, or JAX.
• Comfort iterating quickly between simulation and real-world validation.
• Familiarity with sim-to-real transfer challenges like domain randomization and system identification.

Responsibilities

• Design and run experiments training robotics policies (imitation learning, reinforcement learning, VLA models) primarily in simulation.
• Work hands-on with physical robots to collect real-world data and validate sim-trained policies.
• Collaborate with Dynamics team to identify simulation fidelity gaps affecting transfer performance and prioritize fixes.
• Build and maintain data pipelines and evaluation frameworks/benchmarks for policy training and transfer performance.
• Prototype new tasks and domains grounded in real customer use cases to expand platform capabilities.
• Read, evaluate, and adapt techniques from state-of-the-art robot learning research for Zeromatter's platform.
• Contribute findings to customer-facing materials and demonstrations.
• Build reusable libraries and tooling (in Python, Rust, and/or C++) to support work at scale.

Skills

Robot learning

Python

Rust

C++

PyTorch

TensorFlow

JAX

Simulation

Reinforcement learning

Imitation learning

Domain randomization

Dexterous manipulation

Cross-embodiment transfer

Publications

Education

Engineering degree in robotics/CS/related field

Tools

MuJoCo

Isaac Sim

Python

Rust

C++

PyTorch

TensorFlow

JAX

Job description

Zeromatter Technologies Inc. is seeking a Robotics Research Engineer to design, train, and evaluate robotics policies—from imitation to reinforcement learning—to advance Zeromatter's simulation platform and its real-world validation across customer use cases.

You will collaborate with the Dynamics team to improve physics-based simulation fidelity, run experiments in simulation and the lab, and build scalable tooling in Python, Rust, and C++.